工具

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Add authentication and authorization to routes, Server Actions, and API endpoints using Supabase Auth. Use when user needs "protect [route]", "add authentication", "require login", "add RBAC", "implement login/logout", or mentions auth, permissions, OAuth, API keys. Provides patterns for protected routes, Server Action auth checks, role-based access control (5 roles), OAuth providers (Google, GitHub), email verification, password strength, account lockout, and API key authentication. Do NOT use when building new features (use worldcrafter-feature-builder which can add auth), database-only changes (use worldcrafter-database-setup for RLS policies), routes without auth (use worldcrafter-route-creator), or testing only (use worldcrafter-test-generator).

Reference the project's defined technology stack including frameworks, languages, databases, testing tools, and deployment infrastructure. Use this skill when making technology decisions or choosing libraries. When working with project configuration files like package.json, requirements.txt, or Gemfile. When setting up new features that need to align with existing technology choices. When onboarding to understand the project's technical foundation. When choosing tools for testing, linting, CI/CD, or third-party services.

Secure dotfiles management with chezmoi. Use when helping users initialize chezmoi repositories, add/manage dotfiles, handle secrets with age encryption, create templates for multi-machine configs, troubleshoot chezmoi issues, or review dotfiles for security. Always checks for security implications before adding files.

Generate GitHub issues from an approved engineering specification. Use to break down a spec into implementable, atomic tasks with dependencies, sizing, and labels.

Generate diagrams and flowcharts from mermaid definitions using the mermaid-cli (mmdc). Supports themes, custom CSS, and various output formats including SVG, PNG, and PDF. Mermaid supports 20+ diagram types including flowcharts, sequence diagrams, class diagrams, state diagrams, entity relationship diagrams, user journeys, Gantt charts, pie charts, quadrant charts, requirement diagrams, GitGraph, C4 diagrams, mindmaps, timelines, ZenUML, Sankey diagrams, XY charts, block diagrams, packet diagrams, Kanban boards, architecture diagrams, radar charts, and treemaps. This skill is triggered when the user says things like "create a diagram", "make a flowchart", "generate a sequence diagram", "create a mermaid chart", "visualize this as a diagram", "render mermaid code", or "create an architecture diagram".

Comprehensive Django development guidelines for Pantas Green emissions tracking platform.Use when: writing Django models, views, serializers, migrations, ORM queries, templates, or any Python backend code.Triggers: django, model, view, serializer, migration, ORM, queryset, endpoint, API, DRF, emission, carbon, python backend, template, admin

A simple example Skill demonstrating basic functionality

Expert knowledge of WAI-ARIA (Accessible Rich Internet Applications). Use when users ask about ARIA roles, states, properties, accessible name computation, ARIA attributes (aria-label, aria-labelledby, aria-describedby, etc.), widget roles, landmark roles, live regions, ARIA best practices, or how to implement accessible interactive components. Also use for questions about ARIA specifications, API mappings (core-aam, html-aam), digital publishing ARIA (dpub-aria), graphics ARIA, or any ARIA implementation questions.

Enforces TypeScript strict mode compliance, eliminates any types, ensures type safety, and maintains strict linting standards. Use when TypeScript errors occur, any types need elimination, or strict mode compliance is required.

Incident response playbook templates for Kubernetes. Detection, containment, remediation, and post-incident procedures with decision trees and validation steps.

Create a C# server-side simulation service following the Plugin/IEventAdapter pattern with configuration, pulse updates, and entity management. Use when creating new simulations, scenario generators, or test data providers for FAAD HMI server.

This skill should be used when the user asks to 'run a retrospective', 'review this session', 'extract learnings', 'what did we learn', 'analyze our conversation', 'session review', or wants to reflect on work done during the conversation.

Transforms user project requirements into a structured CLAUDE.md context file. Use when starting a new project and need to document project goals, architecture, technical stack, constraints, and conventions. This skill creates the foundational project context file that other skills and agents will reference throughout the project lifecycle.

Deploy Next.js applications (App Router and Pages Router) to Cloudflare Workers using the OpenNext adapter. This skill should be used when deploying Next.js apps with SSR, ISR, or server components to Cloudflare's serverless platform. It covers setup for both new and existing projects, configuration requirements, development workflows, integration with Cloudflare services (D1, R2, KV, Workers AI), and prevention of 10+ documented errors including worker size limits, runtime compatibility, database connection scoping, and security vulnerabilities.Keywords: Cloudflare Next.js, OpenNext Cloudflare, @opennextjs/cloudflare, Next.js Workers, Next.js App Router Cloudflare, Next.js Pages Router Cloudflare, Next.js SSR Cloudflare, Next.js ISR, server components cloudflare, server actions cloudflare, Next.js middleware workers, nextjs d1, nextjs r2, nextjs kv, Next.js deployment, opennextjs-cloudflare cli, nodejs_compat, worker size limit, next.js runtime compatibility, database connection scoping, Next.js migration

This skill should be used when the user asks to "create a feature branch", "start a new feature", "sync my branch", "sync with main", "update from main", "create a PR", "create a pull request", "ship a feature", "merge and clean up", "handle merge conflicts", "resolve conflicts in git-town", "create stacked branches", "work on dependent features", "configure git-town", "set up git-town", "use git-town offline", "manage git workflow", or mentions git-town commands (hack, sync, propose, ship, continue, undo, kill).

Coordinate Claude Code skills with OpenAI Codex autonomous workflows for end-to-end ATFT-GAT-FAN maintenance.

Revenue operations intelligence for sales/marketing/CS leaders managing E-rate seasonal patterns, customer health scoring, proposal automation, and marketing content generation in K-12 rural broadband market

Read Outlook calendar events via ICS subscription. Use when user asks about meetings, schedule, calendar, appointments, or availability.

Generates comprehensive planning documentation for web application projects, structuring work into context-safe phases with built-in verification criteria. Creates IMPLEMENTATION_PHASES.md, DATABASE_SCHEMA.md, API_ENDPOINTS.md, ARCHITECTURE.md, and other planning docs based on project needs. Optimized for Cloudflare Workers + Vite + React stack. Use when starting new projects, adding major features, or restructuring existing work into manageable phases.Keywords: project planning, planning documentation, IMPLEMENTATION_PHASES.md, DATABASE_SCHEMA.md, API_ENDPOINTS.md, ARCHITECTURE.md, UI_COMPONENTS.md, TESTING.md, AGENTS_CONFIG.md, phased development, context-safe phases, verification criteria, exit criteria, planning docs generator, web app planning, Cloudflare Workers planning, Vite React planning, project structure, project phases, major features planning, new project setup